Removing Dust from CMB Observations with Diffusion Models

TL;DR

This paper explores diffusion models for accurately separating Galactic dust foregrounds from CMB observations, improving component separation and cosmological inference in cosmology.

Contribution

It introduces a diffusion-based approach for modeling dust foregrounds that directly samples from the posterior, enhancing component separation in CMB analysis.

Findings

Diffusion models can recover dust and CMB components effectively.

The method outperforms single-cosmology models in component separation.

Summary statistics like power spectrum are well preserved.

Abstract

In cosmology, the quest for primordial $B$-modes in cosmic microwave background (CMB) observations has highlighted the critical need for a refined model of the Galactic dust foreground. We investigate diffusion-based modeling of the dust foreground and its interest for component separation. Under the assumption of a Gaussian CMB with known cosmology (or covariance matrix), we show that diffusion models can be trained on examples of dust emission maps such that their sampling process directly coincides with posterior sampling in the context of component separation. We illustrate this on simulated mixtures of dust emission and CMB. We show that common summary statistics (power spectrum, Minkowski functionals) of the components are well recovered by this process. We also introduce a model conditioned by the CMB cosmology that outperforms models trained using a single cosmology on component separation. Such a model will be used in future work for diffusion-based cosmological inference.